AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning to Film From Professional Human Motion Videos

Chong Huang, Chuan-En Lin, Zhenyu Yang, Yan Kong, Peng Chen, Xin Yang, Kwang-Ting Cheng

CVPR 2019 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 35 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the proposed imitation-filming system instead of Huang et al. [17]Autonomous drone cinematography · Drone cinematography user studysubjective quality score: 3.15±0.24 -> 4.29±0.54Improved
Use the proposed imitation-filming system instead of ActiveTrackAutonomous drone cinematography · Drone cinematography user studysubjective quality score: 2.64±0.37 -> 4.29±0.54Improved
Add subject-motion prediction loss (ablation)Proposed imitation model · Aerial-video test setoptical-flow prediction error: 3.93%∼10.20%Improved
Use optical flow, background features, and subject-motion features together rather than fewer input types (ablation)Proposed imitation model · Aerial-video test setAEEImproved
Use optical flow as the only input instead of background features or subject-motion features alone (ablation)Proposed imitation model · Aerial-video test setAEEImproved
Set the input and prediction sequence lengths to M=9 and N=9 (ablation)Proposed imitation model · Aerial-video test setAEEImproved
Increase prediction horizon length (ablation)Proposed imitation model · Aerial-video test setAEEHurt
Increase input length beyond the selected setting (ablation)Proposed imitation model · Aerial-video test setAEEMixed
Train on aerial videos rather than handheld videos (ablation)Proposed imitation model · Aerial-video test setoptical-flow prediction errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy